A5058360502- Fire Detection and Safety Systems
- Video Surveillance and Tracking Methods
- Evacuation and Crowd Dynamics
- IoT-based Smart Home Systems
- Stock Market Forecasting Methods
- Sentiment Analysis and Opinion Mining
- Fire dynamics and safety research
- Fire effects on ecosystems
- Context-Aware Activity Recognition Systems
- Lung Cancer Diagnosis and Treatment
- COVID-19 diagnosis using AI
- Cutaneous Melanoma Detection and Management
- Radiomics and Machine Learning in Medical Imaging
- Sleep and Work-Related Fatigue
- Advanced Text Analysis Techniques
- Hate Speech and Cyberbullying Detection
- Water Quality Monitoring Technologies
- melanin and skin pigmentation
- IoT and GPS-based Vehicle Safety Systems
- AI in cancer detection
- Ergonomics and Musculoskeletal Disorders
- IoT and Edge/Fog Computing
Sejong University
2021-2024
Islamia College University
2020-2023
Smart home applications are ubiquitous and have gained popularity due to the overwhelming use of Internet Things (IoT)-based technology. The revolution in technologies has made homes more convenient, efficient, even secure. need for advancement smart technology is necessary scarcity intelligent that cater several aspects simultaneously, i.e., automation, security, safety, reducing energy consumption using less bandwidth, computation, cost. Our research work provides a solution these problems...
Fire detection and management is very important to prevent social, ecological, economic damages. However, achieving real-time fire with higher accuracy in an IoT environment a challenging task due limited storage, transmission, computation resources. To overcome these challenges, early automatic response are significant. Therefore, we develop novel framework based on lightweight convolutional neural network (CNN), requiring less training time, it applicable over resource-constrained devices....
Vision-based fire detection systems have been significantly improved by deep models; however, higher numbers of false alarms and a slow inference speed still hinder their practical applicability in real-world scenarios. For balanced trade-off between computational cost accuracy, we introduce dual attention network (DFAN) to achieve effective yet efficient detection. The first mechanism highlights the most important channels from features an existing backbone model, yielding emphasized...
Nowadays, the use of public transportation is reducing and people prefer to private transport because its low cost, comfortable ride, personal preferences. However, causes numerous real-world road accidents due conditions drivers’ state such as drowsiness, stress, tiredness, age during driving. In cases, driver fatigue detection mandatory avoid ensure a journey. To date, several complex systems have been proposed that problems practicing hand feature engineering tools, causing lower...
Nowadays, the care of elderly peoples is a significant problem and needs more time attention from caregivers. In population, accidental fall common cause injury due to weakness or any other disease such as high temperature blood pressure. Moreover, in developing countries, use natural gas for older adults widespread room heating. The heater can be hazardous, especially at night it has reportedly said turn OFF while going sleep. However, ignored quite often that results many deaths not only...
Abstract Nowadays, political parties have widely adopted social media for their party promotions and election campaigns. During the election, Twitter other platforms are used coverage to promote its candidates. This research discusses estimates stability of many volumetric approaches forecast results from activities. Numerous machine learning applied opinions shared on predicting results. paper presents a model based sentiment analysis predict Pakistan's general In voters vote favorite or...
Skin cancer is actually considered one of the most harmful human types cancer. It exists in many types, but melanoma severe. Early detection valuable for treatment patients. For this function, computer vision plays a major role medical imaging diagnosis Using Jetson Nano, we established an image processing method skin at initial stage proposed work. The research framework consists five phases: collection dermoscopic images, grayscale conversion image, area interest segmentation, and noise...